© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14962
    Prev
    Next
    INDEX
    Explanations

    cocaine, Bolivia, Peru, Andes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oshima
    0.48
     दह
    0.40
    腟
    0.40
    onych
    0.38
     فرا
    0.37
     postponing
    0.37
     undis
    0.36
    ovod
    0.36
     六
    0.36
    xin
    0.36
    POSITIVE LOGITS
     Bolivia
    1.03
     Boliv
    1.02
     Peru
    0.89
    Peru
    0.88
     coca
    0.82
     Peruvian
    0.79
     Perú
    0.78
     Andean
    0.76
     peru
    0.74
     Inca
    0.73
    Activations Density 0.049%

    No Known Activations